Procurement & Supplier Selection

Procurement — Get Engine Script (large files)

procurement_get_engine

Read-only

For delivery histories over 1,000 rows or spend files over 500 items that are already in your code sandbox. Returns a complete, runnable numpy-only Python script with the same engine as procurement_supplier_selection; it reads the file(s), runs the full analysis, prints the decision cards and writes procurement_result.json. Pass the small inputs (criteria, pairwise_comparisons, suppliers, price_breaks ...) in params; they are baked into the script. No supplier data reaches this server on this path.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "procurement_get_engine"
  }
}

Input Schema

Name	Required	Description
`params`	No	All other inputs exactly as procurement_supplier_selection takes them (criteria, pairwise_comparisons, suppliers, price_breaks, annual_demand, order_cost, currency, item_name, ...).
`spend_items_path`	No	Path to the spend file in your sandbox.
`delivery_history_path`	No	Path to the delivery/GRN file (CSV/TSV/JSON) in your sandbox.

Output Schema

Name	Required	Description	Default
`notes`	No
`script`	Yes
`language`	No
`requires`	No
`writes_file`	No
`instructions`	Yes
`engine_version`	Yes
`scipy_required`	No
`spend_items_path`	No
`data_requirements`	No
`delivery_history_path`	No
`network_access_required`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true. The description adds meaningful behavior beyond those hints: the returned script reads sandbox files, runs the full analysis, prints decision cards, writes procurement_result.json, and no supplier data reaches the server on this path. There is no contradiction because the generated script performs the file write, not the MCP tool itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loads the file-size conditions before explaining the returned script. It is dense but mostly wastes nothing; the ellipsis in the parameter examples is slightly loose, but the overall structure is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex code-generation tool, the description covers when to use it, what artifact is returned, what the script does, how parameters are handled, and the key privacy behavior. An output schema exists, so return-value detail is not required, and the remaining context is sufficient to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds a useful semantic point: small inputs such as criteria and pairwise_comparisons are passed in params and are baked into the generated script. The examples partly repeat the schema, but the 'baked into the script' behavior adds meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states that the tool returns a complete, runnable numpy-only Python script for large delivery/spend files already in the sandbox, and it explicitly ties the engine to procurement_supplier_selection. The row/item thresholds and sandbox condition make the scope specific enough to distinguish it from the sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear when-to-use signal: delivery histories over 1,000 rows or spend files over 500 items that are already in the code sandbox. It names the sibling with the same engine, but does not explicitly say to use procurement_supplier_selection for smaller or inline inputs, so the alternative path is implied rather than fully spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Procurement & Supplier Selection tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.